Alternatives and similar repositories for relax

Users that are interested in relax are comparing it to the libraries listed below

• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆108Updated 8 months ago
• mlc-ai / llm-perf-bench
  ☆119Updated last year
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆106Updated 10 months ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆121Updated last month
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆248Updated 6 months ago
• fpgaminer / GPTQ-triton
  GPTQ inference Triton kernel
  ☆299Updated last year
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆92Updated last week
• OpenPPL / ppl.llm.serving
  ☆127Updated 4 months ago
• ROCm / aotriton
  Ahead of Time (AOT) Triton Math Library
  ☆63Updated this week
• NVIDIA / online-softmax
  Benchmark code for the "Online normalizer calculation for softmax" paper
  ☆91Updated 6 years ago
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆54Updated 3 months ago
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆117Updated last month
• bytedance / ByteMLPerf
  AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…
  ☆239Updated 3 weeks ago
• TiledTensor / TiledCUDA
  We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …
  ☆181Updated 3 months ago
• InternLM / turbomind
  ☆84Updated last month
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆36Updated 2 months ago
• xlite-dev / ffpa-attn-mma
  📚FFPA(Split-D): Extend FlashAttention with Split-D for large headdim, O(1) GPU SRAM complexity, 1.8x~3x↑🎉 faster than SDPA EA.
  ☆171Updated last month
• IntelLabs / FP8-Emulation-Toolkit
  PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.
  ☆110Updated 5 months ago
• mlc-ai / mlc-python
  ☆32Updated this week
• triton-lang / triton-cpu
  An experimental CPU backend for Triton
  ☆111Updated 2 weeks ago
• AlibabaPAI / FLASHNN
  ☆94Updated 8 months ago
• OpenPPL / ppl.pmx
  ☆58Updated 5 months ago
• daquexian / faster-rwkv
  ☆124Updated last year
• OpenPPL / ppl.llm.kernel.cuda
  ☆148Updated 4 months ago
• nod-ai / SHARK-ModelDev
  Unified compiler/runtime for interfacing with PyTorch Dynamo.
  ☆100Updated 2 months ago
• BBuf / tensorrt-llm-moe
  ☆28Updated 3 months ago
• ColfaxResearch / cfx-article-src
  ☆104Updated last week
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆473Updated last year
• tpoisonooo / llama.onnx
  LLaMa/RWKV onnx models, quantization and testcase
  ☆363Updated last year